First, we build the basic tuna model with all the predictors included. Note that the environmental predictors are mean values over 1956-1981.
## [1] "training AUC: 0.8861"
## [1] "testing AUC: 0.8169"
Then, we extrapolate for the rest of \(40^{\circ}N\)-\(40^{\circ}S\) and present seasonal distribution maps.
## [1] "training AUC: 0.8769"
## [1] "testing AUC: 0.801"
First, we build the \(10 \times 10\) grid.
Then, we associate the \(10 \times 10\) grid with the \(1 \times 1\) grid cells. This just shows the Jan-March grid. The remaining \(10 \times 10\) grid cells are ones that have sampling points in them.
We visualize this filtered grid overlaid with the distribution map for January-March of model 1 (including all predictors).
Then, we leave only those \(10 \times
10\) grid cells with >25% of its area containing sampling
points.
Then, we do this separately per season and replicate this method across all the species.